{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-snitch",
    "name": "Openclaw Snitch",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/rgr4y/openclaw-snitch",
    "canonicalUrl": "https://clawhub.ai/rgr4y/openclaw-snitch",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-snitch",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-snitch",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "openclaw.plugin.json",
      "docs/plans/2026-02-25-openclaw-snitch.md",
      "README.md",
      "package-lock.json",
      "package.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/openclaw-snitch"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/openclaw-snitch",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-snitch/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-snitch/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-snitch/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "openclaw-snitch",
        "body": "A configurable blocklist guard for OpenClaw with three enforcement layers:\n\nBootstrap directive — injects a security policy into every agent context\nMessage warning — flags incoming messages referencing blocked terms\nHard block — intercepts and kills the tool call + broadcasts a Telegram alert"
      },
      {
        "title": "Hooks (bootstrap + message guard)",
        "body": "After installing this skill, copy the hook directories into your workspace:\n\ncp -r ~/.openclaw/workspace/skills/openclaw-snitch/hooks/snitch-bootstrap ~/.openclaw/hooks/snitch-bootstrap\ncp -r ~/.openclaw/workspace/skills/openclaw-snitch/hooks/snitch-message-guard ~/.openclaw/hooks/snitch-message-guard\n\nThen enable them in openclaw.json:\n\n{\n  \"hooks\": {\n    \"snitch-bootstrap\": { \"enabled\": true },\n    \"snitch-message-guard\": { \"enabled\": true }\n  }\n}"
      },
      {
        "title": "Plugin (hard block + Telegram alert)",
        "body": "For the hard enforcement layer, install the npm package:\n\nnpm install -g openclaw-snitch\n\nThen add to openclaw.json:\n\n{\n  \"plugins\": {\n    \"allow\": [\"openclaw-snitch\"]\n  }\n}\n\nLock down the plugin files after install so the agent can't self-modify:\n\nchmod -R a-w ~/.openclaw/extensions/openclaw-snitch"
      },
      {
        "title": "Configuration",
        "body": "In openclaw.json under plugins.config.openclaw-snitch:\n\n{\n  \"plugins\": {\n    \"config\": {\n      \"openclaw-snitch\": {\n        \"blocklist\": [\"clawhub\", \"clawdhub\"],\n        \"alertTelegram\": true,\n        \"bootstrapDirective\": true\n      }\n    }\n  }\n}\n\nKeyDefaultDescriptionblocklist[\"clawhub\", \"clawdhub\"]Terms to block (case-insensitive word boundary match)alertTelegramtrueBroadcast Telegram alert to all allowFrom IDs on blockbootstrapDirectivetrueInject security directive into every agent bootstrap context"
      },
      {
        "title": "Hook blocklist (env var)",
        "body": "The hooks read SNITCH_BLOCKLIST (comma-separated) if set, otherwise fall back to the defaults:\n\nSNITCH_BLOCKLIST=clawhub,clawdhub,myothertool"
      },
      {
        "title": "What gets blocked",
        "body": "Blocks fire when the tool name or tool parameters contain a blocked term. This catches cases where an agent tries to invoke a blocked tool indirectly (e.g. exec with clawhub install in the args)."
      },
      {
        "title": "Security notes",
        "body": "The hooks in ~/.openclaw/hooks/ load unconditionally — most tamper-resistant layer\nThe plugin layer requires plugins.allow — if an agent edits openclaw.json, hooks remain active\nchown root:root on the extension dir prevents the agent from self-modifying the plugin"
      }
    ],
    "body": "openclaw-snitch\n\nA configurable blocklist guard for OpenClaw with three enforcement layers:\n\nBootstrap directive — injects a security policy into every agent context\nMessage warning — flags incoming messages referencing blocked terms\nHard block — intercepts and kills the tool call + broadcasts a Telegram alert\nInstall\nHooks (bootstrap + message guard)\n\nAfter installing this skill, copy the hook directories into your workspace:\n\ncp -r ~/.openclaw/workspace/skills/openclaw-snitch/hooks/snitch-bootstrap ~/.openclaw/hooks/snitch-bootstrap\ncp -r ~/.openclaw/workspace/skills/openclaw-snitch/hooks/snitch-message-guard ~/.openclaw/hooks/snitch-message-guard\n\n\nThen enable them in openclaw.json:\n\n{\n  \"hooks\": {\n    \"snitch-bootstrap\": { \"enabled\": true },\n    \"snitch-message-guard\": { \"enabled\": true }\n  }\n}\n\nPlugin (hard block + Telegram alert)\n\nFor the hard enforcement layer, install the npm package:\n\nnpm install -g openclaw-snitch\n\n\nThen add to openclaw.json:\n\n{\n  \"plugins\": {\n    \"allow\": [\"openclaw-snitch\"]\n  }\n}\n\n\nLock down the plugin files after install so the agent can't self-modify:\n\nchmod -R a-w ~/.openclaw/extensions/openclaw-snitch\n\nConfiguration\n\nIn openclaw.json under plugins.config.openclaw-snitch:\n\n{\n  \"plugins\": {\n    \"config\": {\n      \"openclaw-snitch\": {\n        \"blocklist\": [\"clawhub\", \"clawdhub\"],\n        \"alertTelegram\": true,\n        \"bootstrapDirective\": true\n      }\n    }\n  }\n}\n\nKey\tDefault\tDescription\nblocklist\t[\"clawhub\", \"clawdhub\"]\tTerms to block (case-insensitive word boundary match)\nalertTelegram\ttrue\tBroadcast Telegram alert to all allowFrom IDs on block\nbootstrapDirective\ttrue\tInject security directive into every agent bootstrap context\nHook blocklist (env var)\n\nThe hooks read SNITCH_BLOCKLIST (comma-separated) if set, otherwise fall back to the defaults:\n\nSNITCH_BLOCKLIST=clawhub,clawdhub,myothertool\n\nWhat gets blocked\n\nBlocks fire when the tool name or tool parameters contain a blocked term. This catches cases where an agent tries to invoke a blocked tool indirectly (e.g. exec with clawhub install in the args).\n\nSecurity notes\nThe hooks in ~/.openclaw/hooks/ load unconditionally — most tamper-resistant layer\nThe plugin layer requires plugins.allow — if an agent edits openclaw.json, hooks remain active\nchown root:root on the extension dir prevents the agent from self-modifying the plugin"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/rgr4y/openclaw-snitch",
    "publisherUrl": "https://clawhub.ai/rgr4y/openclaw-snitch",
    "owner": "rgr4y",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-snitch",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-snitch",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-snitch/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-snitch/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-snitch/agent.md"
  }
}